Unconstrained ear detection using ensemble‐based convolutional neural network model

Abstract

This paper presents a technique for ear detection from 2D profile face images that is capable of significantly reducing the false positives. In an ear biometrics system, recognition performance highly depends on the performance of the ear detection module. The trade-off between the complexity and the false positive detection is one of the essential component, where the complexity of a system increases proportionally to achieve a zero false positive rate detection.In literature, available ear detection techniques based on handcrafted features face challenges with low-quality acquired images affected by illumination, occlusion, and pose variations. We propose an ear detection technique using ensemble of convolutional neural network (CNN). The first part of the technique trains three models of CNN on a given dataset, whereas in later part, weighted average of the outputs of trained models is utilized to detect the ear regions. The used ensemble models show better performance as compared to the case when each individual model is used standalone. The proposed technique is being evaluated on two databases, viz, IIT Indore-Collection A (IIT-Col A) database and annotated web ear (AWE) database. Experimental results of ear detection demonstrate the superior performance of the proposed technique over other state-of-the-art techniques in handling illumination, occlusion, and pose variations. KEYWORDS deep learning, ear detection, ensemble model, unconstrained environment INTRODUCTIONIn recent years, ear biometrics has been considered a reliable biometrics and has got attention over face mainly due to its invariant behavior to the age of a person. Biometrics systems based on face have to consider the changes occurring in the face with a change in age or expression.The ear of a person remains consistent in its shape and it is fixed in its position at the center of the profile image. To obtain reliable performance, face images are required to be captured in the controlled setting, while in case of ear, it can be captured with a foreseeable background due to its fixed side face background. An ear biometric system mainly consists of two processes, ie, Ear detection and Ear recognition. Majority of the ear biometrics techniques in the literature use manually cropped ear images to perform ear recognition process. Furthermore, the ear biometric techniques that crops ear automatically are able to detect ear only when the ear has small variations in the side face image. In cases of pose or scale variations, these techniques are found to be inefficient. Additionally, in a real-time environment, these techniques lack in being fully automatic approaches and speed.Performance of an ear detection technique based on handcrafted feature learning methods depends on the dataset used for learning the features. 1 These methods are prone to produce erroneous results when used with the images captured in unconstrained settings like different illumination, background, and pose. Tasks like extraction of suitable features along with the discriminati...

A comprehensive survey and deep learning-based approach for human recognition using ear biometric

“… [ 69 ] UND AMI UBEAR Video Spatial Contrastive Normalisation Average of 3 CNN Not Mentioned UBEAR:75, AMI:99, UND:95, Video:94 5. [ 79 ] AWE and IIT Indore Nil Average ensemble of CNN models Intersection over Union 99.52 6. [ 70 ] IITK,UND-J2, UBEAR Nil Context-aware CNN Intersection over Union IITK: 99.10, UND-J2: 97.15, UBEAR: 99.92 The column “Database” represents the database used for training and testing, the column “Pre-processing” represents the technique used to pre-process the images for better features representation, the column “Technique” specifies the method used by the authors, the column “Evaluation Criteria” is the method used for evaluation of correct ear detection, and the last column “Accuracy” denotes the performance of the system …”

Estimation of Indoor Location Through Magnetic Field Data: An Approach Based On Convolutional Neural Networks

“…They are characterized by having up to five base layers, including an input layer, a convolutional neural layer, a pooling layer, a fully connected layer and an output layer. Also, CNN presents the important characteristic of extracting abstract features directly from the input data, achieving important contributions, mainly in different computer fields, such as classification, detection and segmentation of data [30]. This method, like other similar methods, uses a two-stage process: a feature learning stage and a classification stage.…”

Ear Detection Using Convolutional Neural Network on Graphs with Filter Rotation

“…A detection technique applying an ensemble of convolutional neural networks (CNNs) was presented in [11]. The weighted average of the outputs of three trained CNNs was considered as result of detection of the ear regions.…”